Upload 7 files

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8adaec7186df22f9b299c660496e2373f43b318bb3506d62980c417b8b7b66
+size 128593361

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e7a5255e8a381596fb94deeca91fb19f81d7e5dc1eeffe9ee6dc99c55a4162
+size 64310119

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aabd859ef3cd665de6dd114cee226bcbbba4d9f79b32cffa5d9eab8ddee59d
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be64bbbdcbd881984384811f1883ed7c22bd25f66bf82b503095da78c6aef008
+size 623

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 7448370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.5e-05,
+      "loss": 5.1426,
+      "step": 744837
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4e-05,
+      "loss": 4.3897,
+      "step": 1489674
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-05,
+      "loss": 4.271,
+      "step": 2234511
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 4.2161,
+      "step": 2979348
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 4.174,
+      "step": 3724185
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2e-05,
+      "loss": 4.1243,
+      "step": 4469022
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.5e-05,
+      "loss": 4.0682,
+      "step": 5213859
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 4.0117,
+      "step": 5958696
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 5e-06,
+      "loss": 3.9571,
+      "step": 6703533
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 3.9111,
+      "step": 7448370
+    }
+  ],
+  "max_steps": 7448370,
+  "num_train_epochs": 10,
+  "total_flos": 1.4787097128956529e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6651d474e06685343ab7aa3db3fdedd72888651138eb02cae13b4dfdce2a8541
+size 2991